{"id":"https://openalex.org/W7129177026","doi":"https://doi.org/10.1109/tsc.2026.3665441","title":"Retrieval-Augmented Generation for Service Discovery: Chunking Strategies and Benchmarking","display_name":"Retrieval-Augmented Generation for Service Discovery: Chunking Strategies and Benchmarking","publication_year":2026,"publication_date":"2026-02-16","ids":{"openalex":"https://openalex.org/W7129177026","doi":"https://doi.org/10.1109/tsc.2026.3665441"},"language":null,"primary_location":{"id":"doi:10.1109/tsc.2026.3665441","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsc.2026.3665441","pdf_url":null,"source":{"id":"https://openalex.org/S204223317","display_name":"IEEE Transactions on Services Computing","issn_l":"1939-1374","issn":["1939-1374","2372-0204"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Services Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011425750","display_name":"Robin D. Pesl","orcid":"https://orcid.org/0000-0002-5980-9395"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Robin D. Pesl","raw_affiliation_strings":["Institute of Architecture of Application Systems, University of Stuttgart, Stuttgart, Germany"],"raw_orcid":"https://orcid.org/0000-0002-5980-9395","affiliations":[{"raw_affiliation_string":"Institute of Architecture of Application Systems, University of Stuttgart, Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018276312","display_name":"Jerin George Mathew","orcid":"https://orcid.org/0000-0002-4626-826X"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Jerin G. Mathew","raw_affiliation_strings":["Dipartimento di Ingegneria Informatica, Sapienza Università di Roma, Rome, Italy"],"raw_orcid":"https://orcid.org/0000-0002-4626-826X","affiliations":[{"raw_affiliation_string":"Dipartimento di Ingegneria Informatica, Sapienza Università di Roma, Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126112508","display_name":"Massimo Mecella","orcid":null},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Massimo Mecella","raw_affiliation_strings":["Dipartimento di Ingegneria Informatica, Sapienza Università di Roma, Rome, Italy"],"raw_orcid":"https://orcid.org/0000-0002-9730-8882","affiliations":[{"raw_affiliation_string":"Dipartimento di Ingegneria Informatica, Sapienza Università di Roma, Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"last","author":{"id":null,"display_name":"Marco Aiello","orcid":"https://orcid.org/0000-0002-0764-2124"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marco Aiello","raw_affiliation_strings":["Institute of Architecture of Application Systems, University of Stuttgart, Stuttgart, Germany"],"raw_orcid":"https://orcid.org/0000-0002-0764-2124","affiliations":[{"raw_affiliation_string":"Institute of Architecture of Application Systems, University of Stuttgart, Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5011425750"],"corresponding_institution_ids":["https://openalex.org/I100066346"],"apc_list":null,"apc_paid":null,"fwci":69.2675,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.99648172,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"19","issue":"2","first_page":"1520","last_page":"1534"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.42829999327659607,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.42829999327659607,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.09300000220537186,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.05559999868273735,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.7128000259399414},{"id":"https://openalex.org/keywords/chunking","display_name":"Chunking (psychology)","score":0.7016000151634216},{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.6564000248908997},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.614300012588501},{"id":"https://openalex.org/keywords/service-discovery","display_name":"Service discovery","score":0.5925999879837036},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5694000124931335}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8790000081062317},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7128000259399414},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.7016000151634216},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.6564000248908997},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.614300012588501},{"id":"https://openalex.org/C144097018","wikidata":"https://www.wikidata.org/wiki/Q4329404","display_name":"Service discovery","level":3,"score":0.5925999879837036},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5694000124931335},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5091000199317932},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.37860000133514404},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34619998931884766},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3203999996185303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30329999327659607},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsc.2026.3665441","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsc.2026.3665441","pdf_url":null,"source":{"id":"https://openalex.org/S204223317","display_name":"IEEE Transactions on Services Computing","issn_l":"1939-1374","issn":["1939-1374","2372-0204"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Services Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Integrating":[0],"multiple":[1],"(sub-)systems":[2],"is":[3,82],"essential":[4],"to":[5,50,71,86,116,221,228,255],"create":[6],"advanced":[7],"Information":[8],"Systems.":[9],"Difficulties":[10],"mainly":[11],"arise":[12],"when":[13],"integrating":[14],"dynamic":[15],"environments,":[16],"e.g.,":[17],"the":[18,38,42,92,98,109,118,124,131,136,155,188,194,201,208,212,230,259],"integration":[19],"at":[20],"design":[21],"time":[22],"of":[23,41,53,100,113,154],"not":[24],"yet":[25],"existing":[26],"services.":[27],"This":[28],"has":[29],"been":[30],"traditionally":[31],"addressed":[32],"using":[33,171,211],"a":[34,146,152,173,181],"registry":[35],"that":[36,149,236],"provides":[37],"API":[39,78,89],"documentation":[40,65],"endpoints.":[43],"Large":[44],"Language":[45],"Models":[46],"(LLMs)":[47],"have":[48],"shown":[49],"be":[51],"capable":[52],"automatically":[54],"creating":[55],"system":[56],"integrations":[57],"(e.g.,":[58],"as":[59],"service":[60,176],"composition)":[61],"based":[62],"on":[63,163,246],"this":[64],"but":[66],"require":[67],"concise":[68],"input":[69,72,119,132],"due":[70],"token":[73,120,133,231],"limitations,":[74],"especially":[75],"regarding":[76],"comprehensive":[77],"descriptions.":[79,90],"Currently,":[80],"it":[81],"unknown":[83],"how":[84,220],"best":[85],"preprocess":[87],"these":[88],"In":[91],"present":[93],"work,":[94],"we":[95,143,206],"(i)":[96],"analyze":[97],"usage":[99],"Retrieval":[101],"Augmented":[102],"Generation":[103],"(RAG)":[104],"for":[105,135,168,193,225,243,261],"endpoint":[106,141,169,202,226],"discovery":[107,170,177,227],"and":[108,139,159,187,198],"chunking,":[110],"i.e.,":[111],"preprocessing,":[112],"state-of-practice":[114],"OpenAPIs":[115],"reduce":[117,130,229],"length":[121,134],"while":[122,252],"preserving":[123],"most":[125,156],"relevant":[126,157],"information.":[127],"To":[128],"further":[129,262],"composition":[137],"prompt":[138],"improve":[140],"retrieval,":[142],"propose":[144],"(ii)":[145],"Discovery":[147,209],"Agent":[148,210],"only":[150],"receives":[151],"summary":[153],"endpoints":[158],"retrieves":[160],"specification":[161],"details":[162],"demand.":[164],"We":[165],"evaluate":[166],"RAG":[167,224],"(iii)":[172],"proposed":[174],"novel":[175],"benchmark":[178],"SOCBench-D":[179],"representing":[180],"general":[182],"setting":[183],"across":[184],"numerous":[185],"domains":[186],"real-world":[189],"RestBench":[190],"benchmark,":[191],"first,":[192],"different":[195],"chunking":[196,241],"possibilities":[197],"parameters":[199],"measuring":[200],"retrieval":[203],"accuracy.":[204],"Then,":[205],"assess":[207],"same":[213],"test":[214],"data":[215],"set.":[216],"The":[217],"prototype":[218],"shows":[219],"successfully":[222],"employ":[223],"count.":[232],"Our":[233],"experiments":[234],"show":[235],"endpoint-based":[237],"approaches":[238],"outperform":[239],"na\u00fcve":[240],"methods":[242],"preprocessing.":[244],"Relying":[245],"an":[247],"agent":[248],"significantly":[249],"improves":[250],"precision":[251],"being":[253],"prone":[254],"decrease":[256],"recall,":[257],"disclosing":[258],"need":[260],"reasoning":[263],"capabilities.":[264]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-11T06:13:24.991567","created_date":"2026-02-17T00:00:00"}